• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.653-662
• /
• 1989

Cerebellar Model Arithmetic Controller (CMAC) has been introduced as an adaptive control function generator. CMAC computes control functions referring to a distributed memory table storing functional values rather than by solving equations analytically or numerically. CMAC has a unique mapping structure as a coarse coding and supervisory delta-rule learning property. In this paper, learning aspects and a convergence of the CMAC were investigated. The efficient training algorithms were developed to overcome the limitations caused by the conventional maximum error correction training and to eliminate the accumulated learning error caused by a sequential node training. A nonlinear function generator and a motion generator for a two d.o.f. manipulator were simulated. The efficiency of the various learning algorithms was demonstrated through the cpu time used and the convergence of the rms and maximum errors accumulated during a learning process. A generalization property and a learning effect due to the various gains were simulated. A uniform quantizing method was applied to cope with various ranges of input variables efficiently.

• Korean Management Science Review
• /
• v.18 no.2
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• 한국기계연구소 소보
• /
• s.19
• /
• pp.93-115
• /
• 1989

Cerebellar Model Arithmetic Controller(CMAC) has been introduced as an adaptive control function generator. CMAC computes control functions referring to a distributed memory table storing functional values rather than by solving equations analytically or numerically. CMAC has a unique mapping structure as a coarse coding and supervisory delta-rule learning property. In this paper, learning aspects and a convergence of the CMAC were investigated. The efficient training algorithms were developed to overcome the limitations caused by the conventional maximum error correction training and to eliminate the accumulated learning error caused by a sequential node training. A nonlinear function generator and a motion generator for a two d. o. f. manipulator were simulated. The efficiency of the various learning algorithms was demonstrated through the cpu time used and the convergence of the rms and maximum errors accumulated during a learning process; A generalization property and a learning effect due to the various gains were simulated. A uniform quantizing method was applied to cope with various ranges of input variables efficiently.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.399-403
• /
• 1998

In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.6
• /
• pp.82-86
• /
• 2005

PID controller is widely used as automatic equipment for industry. However when a system has various characters of intermittence or continuance, a new parameter decision for accurate control is a bud task. As a method of solving this problem, in this paper, a teaming gain regulator as PID controller functions is presented. A propriety teaming gain of system is decided by a rule of Delta learning. The function of proposed loaming gain regulator is verified by simulation results of DC motor.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.408-411
• /
• 1993

In this paper, we propose the Fuzzy Neural Controller with a Self-Organizing Map based on the fuzzy relation neuron. The fuzzy ndes expressing the input-output relation of the system are obtained by using the fuzzy relation neuron and updated automatically by means of the generalized delta rule. Also, the proposed method has a capability to express the knowledge acquired from the input-output data in form of fuzzy inferences rules. The learning algorithm of this fuzzy relation neuron is described. The effectiveness of the proposed fuzzy neural controller is illustrated by applying it to a number of test data sets.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.12 no.11
• /
• pp.1038-1047
• /
• 2000

The objective of this study is to develop an optimized Artificial Neural Network(ANN) model to predict the descending time of room air temperature. For this, program for predicting room air temperature and ANN program using generalized delta rule were collected through simulation for predicting room air temperature. ANN was trained and the ANN model having the optimized values-learning rate, moment, bias, number of hidden layer, and number of neuron of hidden layer was presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.14-24
• /
• 2002

In this paper, a design of the pulsewidth-modulation(PWM) neural network with both retrieving and learning function is proposed. In the designed PWM neural system, the input and output signals of the neural network are represented by PWM signals. In neural network, the multiplication is one of the most commonly used operations. The multiplication and summation functions are realized by using the PWM technique and simple mixed-mode circuits. Thus, the designed neural network only occupies the small chip area. By applying some circuit design techniques to reduce the nonideal effects, the designed circuits have good linearity and large dynamic range. Moreover, the delta learning rule can easily be realized. To demonstrate the learning capability of the realized PWM neural network, the delta learning nile is realized. The circuit with one neuron, three synapses, and the associated learning circuits has been designed. The HSPICE simulation results on the two learning examples on AND function and OR function have successfully verified the function correctness and performance of the designed neural network.

• Proceedings of the KIPE Conference
• /
• 1998.07a
• /
• pp.384-387
• /
• 1998

This paper presents a newly developed speed sensorless drive using RLS(Recursive Least Squares) based on Neural Network Training Algorithm. The proposed algorithm based on the RLS has just the time-varying learning rate, while the well-known back-propagation (or generalized delta rule) algorithm based on gradient descent has a constant learning rate. The number of iterations required by the new algorithm to converge is less than that of the back-propagation algorithm. The RLS based on NN is used to adjust the motor speed so that the neural model output follows the desired trajectory. This mechanism forces the estimated speed to follow precisely the actual motor speed. In this paper, a flux estimation strategy using filter concept is discussed. The theoretical analysis and experimental results to verify the effectiveness of the proposed analysis and the proposed control strategy are described.

• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.186-198
• /
• 1990

인간 소뇌의 구조와 기능을 간략하게 수학적으로 모델링하여 입력에 따른 시스템의 적정 출력을 학습에 의한 적응 제어 방식으로 추출해 내는 소뇌모델 대수제어기(CMAC : Cerebellar Model Arithmetic Controller)가 제안되었다. 본 논문에서는 연구개발된 기존 신경회로망과의 비교 분석에 의거하여, 소뇌모델 대수제어기 대신 네트의 특성에 따라 소뇌모델 선형조합 신경망(CMLAN : Cerebellum Model Linear Associator Network)이라 하였다. 소뇌모델 선형조합 신경망은 시스템의 제어 함수치를 결정하는 데 있어, 기존의 제어방식이 시스템의 모델링을 기초로 하여 알고리즘에 의한 수치해석적 또는 분석적 기법으로 모델 해를 산출하는 것과 달리, 학습을 통하여 저장되는 분산기억 소자들의 함수치를 선형적으로 조합함으로써 시스템의 입출력을 결정한다. 분산기억 소자로의 함수치 산정 및 저장은 소뇌모델 선형조합 신경망이 갖는 고유의 구조적 상태공간 매핑(State Space Mapping)과 델타규칙(Delta Rule)에 의거한 시스템의 입출력 상태함수의 학습으로써 수행된다. 본 논문을 통하여 소뇌모델 선형조합신경망의 구조적 특성, 학습 성질과 상태공간 설정 및 시스템의 수렴성을 규명하였다. 또한 기존의 최대 편차수정 학습 알고리즘이 갖는 비능률성 및 적용 제한성을 극복한 효율적 학습 알고리즘들을 제시하였다. 언급한 신경망의 특성 및 제안된 학습 알고리즘들의 능률성을 다양한 학습이득(Learning Gain)하에서 비선형 함수를 컴퓨터로 모의 시험하여 예시하였다.